Robust Detection of Epileptic Seizures Using Deep Neural Networks

Hussein, Ramy; Palangi, Hamid; Wang, Z. Jane; Ward, Rabab K.

doi:10.1109/icassp.2018.8462029

Cited by 25 publications

(37 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare Laelaps with the SoA methods in seizure detection including LBP+SVM [1], and LSTM networks [3]. Besides, we consider CNNs coupled with short time Fourier transform (STFT) that is proposed as a universal method for seizure prediction [2].…”

Section: B Results: Sensitivity False Alarms and Detection Delaymentioning

confidence: 99%

“…For improved monitoring of these patients with drug-resistant epilepsy-e.g., during presurgical diagnosticsmachine learning methods are developed for automatic seizure detection. These SoA methods are based on extracting useful features followed by traditional supervised machine learning methods such as K-nearest neighbor [5], random forest [6], [4], and support vector machines (SVMs) [1], [7]; more recent methods exploit automatic feature extraction algorithms based on deep learning such as convolutional neural networks (CNNs) [2] and long short-term memories (LSTMs) [3].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Laelaps: An Energy-Efficient Seizure Detection Algorithm from Long-term Human iEEG Recordings without False Alarms

Burrello

Cavigelli

Schindler

et al. 2019

2019 Design, Automation &Amp; Test in Europe Conference &Amp; Exhibition (DATE)

View full text Add to dashboard Cite

We propose Laelaps, an energy-efficient and fast learning algorithm with no false alarms for epileptic seizure detection from long-term intracranial electroencephalography (iEEG) signals. Laelaps uses end-to-end binary operations by exploiting symbolic dynamics and brain-inspired hyperdimensional computing. Laelaps's results surpass those yielded by state-of-the-art (SoA) methods [1], [2], [3], including deep learning, on a new very large dataset containing 116 seizures of 18 drug-resistant epilepsy patients in 2656 hours of recordings-each patient implanted with 24 to 128 iEEG electrodes. Laelaps trains 18 patient-specific models by using only 24 seizures: 12 models are trained with one seizure per patient, the others with two seizures. The trained models detect 79 out of 92 unseen seizures without any false alarms across all the patients as a big step forward in practical seizure detection. Importantly, a simple implementation of Laelaps on the Nvidia Tegra X2 embedded device achieves 1.7×-3.9× faster execution and 1.4×-2.9× lower energy consumption compared to the best result from the SoA methods. Our source code and anonymized iEEG dataset are freely available at http://ieeg-swez.ethz.ch.

show abstract

Section: B Results: Sensitivity False Alarms and Detection Delaymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Laelaps: An Energy-Efficient Seizure Detection Algorithm from Long-term Human iEEG Recordings without False Alarms

Burrello

Cavigelli

Schindler

et al. 2019

2019 Design, Automation &Amp; Test in Europe Conference &Amp; Exhibition (DATE)

View full text Add to dashboard Cite

show abstract

“…Hussein et al proposed a robust epilepsy detection system that is capable of handling noisy EEG data using LSTM. A promising result was recorded for noisy data [13]. However, the proposed LSTM network needed three layers to achieve good accuracy.…”

Section: Introductionmentioning

confidence: 98%

Selection of optimal wavelet features for epileptic EEG signal classification with LSTM

Aliyu

Lim

2021

Neural Comput & Applic

View full text Add to dashboard Cite

Epilepsy remains one of the most common chronic neurological disorders; hence, there is a need to further investigate various models for automatic detection of seizure activity. An effective detection model can be achieved by minimizing the complexity of the model in terms of trainable parameters while still maintaining high accuracy. One way to achieve this is to select the minimum possible number of features. In this paper, we propose a long short-term memory (LSTM) network for the classification of epileptic EEG signals. Discrete wavelet transform (DWT) is employed to remove noise and extract 20 eigenvalue features. The optimal features were then identified using correlation and P value analysis. The proposed method significantly reduces the number of trainable LSTM parameters required to attain high accuracy. Finally, our model outperforms other proposed frameworks, including popular classifiers such as logistic regression (LR), support vector machine (SVM), K-nearest neighbor (K-NN) and decision tree (DT).

show abstract

“…Intracranial electroencephalography (iEEG) currently provides the best spatial resolution and the highest signal-tonoise ratio (SNR) to record the brain activity in patients with epilepsy [4]. Using iEEG signals, recent machine learning methods have been successful in detecting ictal state (i.e., during seizures) and interictal state (between seizures) [5], [6], [7]. Some attempts are even made to forecast the seizure state [8], [9].…”

Section: Introductionmentioning

confidence: 99%

“…2) We present an extensive analysis and comparison with the state-of-the-art (SoA) methods. Compared to LBP+HD [12] and to the SoA methods [7], [15], [5], [12], [9], [6], our new algorithm shortens the latency of seizure onset detection (8.81 s vs. 11.57 s) with a higher specificity (97.31% vs. 94.84%) and a slightly lower sensitivity (96.38% vs. 99.77%). 3) Using our algorithm, we demonstrate how specific signal features help to extract clinically useful information.…”

Section: Introductionmentioning

confidence: 99%

An Ensemble of Hyperdimensional Classifiers: Hardware-Friendly Short-Latency Seizure Detection With Automatic iEEG Electrode Selection

Burrello

Benatti

Schindler

et al. 2021

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

We propose an intracranial electroencephalography (iEEG) based algorithm for detecting epileptic seizures with short latency, and with identifying the most relevant electrodes. Our algorithm first extracts three features, namely mean amplitude, line length, and local binary patterns that are fed to an ensemble of classifiers using hyperdimensional (HD) computing. These features are embedded into an HD space where well-defined vector-space operations are used to construct prototype vectors representing ictal (during seizures) and interictal (between seizures) brain states. Prototype vectors can be computed at different spatial scales ranging from a single electrode up to many electrodes covering different brain regions. This flexibility allows our algorithm to identify the iEEG electrodes that discriminate best between ictal and interictal brain states. We assess our algorithm on the SWEC-ETHZ iEEG dataset that includes 99 short-time iEEG seizures recorded with 36 to 100 electrodes from 16 drug-resistant epilepsy patients. Using k-fold crossvalidation and all electrodes, our algorithm surpasses state-ofthe-art algorithms yielding significantly shorter latency (8.81 s vs. 11.57 s) in seizure onset detection, and higher specificity (97.31% vs. 94.84%) and accuracy (96.85% vs. 95.42%). We can further reduce the latency of our algorithm to 3.74 s by allowing a slightly higher percentage of false alarms (2% specificity loss). Using only the top 10% of the electrodes ranked by our algorithm, we still maintain superior latency, sensitivity, and specificity compared to the other algorithms with all the electrodes. We finally demonstrate the suitability of our algorithm to deployment on low-cost embedded hardware platforms, thanks to its robustness to noise/artifacts affecting the signal, its low computational complexity, and the small memory-footprint on a RISC-V microcontroller.

show abstract

Robust Detection of Epileptic Seizures Using Deep Neural Networks

Cited by 25 publications

References 26 publications

Laelaps: An Energy-Efficient Seizure Detection Algorithm from Long-term Human iEEG Recordings without False Alarms

Laelaps: An Energy-Efficient Seizure Detection Algorithm from Long-term Human iEEG Recordings without False Alarms

Selection of optimal wavelet features for epileptic EEG signal classification with LSTM

An Ensemble of Hyperdimensional Classifiers: Hardware-Friendly Short-Latency Seizure Detection With Automatic iEEG Electrode Selection

Contact Info

Product

Resources

About